Book a scoping call
Home / Blog / Grounded Chatbot on Your Own Documents

Grounded Chatbot on Your Own Documents: answers from your own documents, with the source attached

A chatbot that invents an answer is worse than no chatbot. One that quotes your own price book, with the page number, is a different product entirely.

Live example Answers with a source attached
What’s our callout fee after hours in the Sunshine Coast zone?
After-hours callout is $185 inc GST for zone A, which covers the Sunshine Coast. That covers the first 30 minutes on site; labour is charged at the after-hours rate beyond that. [ Price book 2026, p.4 — After-hours rates ]

If the answer is not in your documents, it says so instead of inventing one.

What it actually does

Your own documents are indexed, the relevant passages are retrieved for each question, and the answer is generated only from what was retrieved, with the source shown.

Voice agents, document extraction, retrieval chat over your own material, and assistants with scoped access to your systems. In practice, Grounded Chatbot on Your Own Documents is the version of that we deploy when a business needs the result rather than a project. Built on our ChatVault engine: retrieval with forced citations, and a refusal when retrieval comes back empty.

Why businesses ask for this

AI is worth buying when it removes a specific, repeated, checkable task. It is worth avoiding everywhere else, and we will tell you which is which.

The people who get the most out of it: anyone with a price book, a manual, a policy library or a long FAQ.

  • The repetitive half of a job handled, the judgement half escalated
  • Answers grounded in your documents rather than invented
  • Every automated decision logged so you can read it back

How we build it, step by step

The sequence below is the one we follow on every grounded retrieval build. It is deliberately boring, because the interesting version is the one that breaks in month three.

  1. Gather the source material and decide what is authoritative
  2. Chunk and index it so retrieval returns the right passage, not the right document
  3. Force citations so every answer can be checked against the source
  4. Refuse rather than improvise when retrieval comes back empty
The part most people skip: testing what it refuses. We build a question set that includes things your documents do not answer, and confirm it declines instead of improvising. That behaviour is the whole product.

What we change before it goes live

A reference implementation is a starting line, not a product. Every one we deploy gets the same treatment:

  • Your numbers, your sender identity and your wording, so nothing reads as generic
  • Secrets moved out of the code and into managed configuration
  • Retries, rate limits and idempotency, so a hiccup never sends twice
  • Structured logging and alerting, so a failure is noticed by us and not by a customer
  • Consent, opt-out and record-keeping built in rather than bolted on
  • Source control, a staging environment and a rollback that takes a minute

Compliance and risk

Two failure modes matter: confident wrong answers, and silent scope creep. We bound what the model is allowed to do, log every turn, and set a hard escalation path to a human.

We set the technical controls up correctly and document what we did. We are not lawyers, and anything unusual about your industry gets flagged in writing so you can take advice on it before launch rather than after.

The technical foundation

Open frameworks running on infrastructure you control, a model provider of your choice, and an evaluation set built from your real cases.

What it costs

Three ways to buy this, and the honest recommendation is usually the middle one:

  • Starter build, from $2,500 — we build it, hand it over and warrant it for 30 days. Suits a business with someone technical in-house.
  • Managed, from $390/mo — we build it and then own it: monitoring, changes, compliance upkeep and a monthly report. Suits everyone else.
  • Platform, from $2,400/mo — when this is one of several systems and you want them designed as one layer instead of five.

Platform usage is billed at cost on top and itemised on the invoice. There is no margin on it and no minimum spend.

Common questions

How long does Grounded Chatbot on Your Own Documents take to build?

One to two weeks, depending on how much source material there is and what state it is in. Tidy documents are most of the timeline.

What does it cost to run each month?

Two lines: our managed plan from from $390/mo, and platform usage billed at cost. Usage for this kind of system usually lands between $30 and $300 a month depending on volume. You see both itemised, and the platform account stays in your name.

Do we own it, or are we locked in?

You own it. The account, the numbers, the phone history and the source code are yours, and the foundation is open source. If you take it in-house, we hand over the repository and the runbook and that is the end of the conversation.

What if it breaks at 6pm on a Friday?

It is monitored. Failures raise an alert, the system degrades to something safe rather than silent, and hello@betr.agency is the inbox that answers. That is what the managed plan buys.

Can it work with the systems we already use?

Usually yes. Open frameworks running on infrastructure you control, a model provider of your choice, and an evaluation set built from your real cases. Where a system has no API, we look at whether an export, a shared inbox or a scheduled sync gets you 90 percent of the value for 10 percent of the cost.

Where to next

The product page for this build lists the specification, the timeline and what is included: Grounded Chatbot on Your Own Documents. If you want to talk it through against your actual process, a scoping call is 30 minutes and costs nothing.

[ // / RELATED ]

Builds that pair with this one

Same pattern or same product line, and often bought together.

Want this running in your business?

Tell us what happens today, by hand. We will tell you what it costs to stop doing it.